Data information desensitization method and device, storage medium and processor

Abstract

The embodiment of the invention provides a data information desensitization method and device, a storage medium and a processor. The method comprises the following steps: acquiring data information, and converting the data information into data of a preset type for storage; splitting the stored data based on a preset rule to obtain a plurality of data blocks; inputting each data block into a pre-trained generative adversarial neural network for processing by adopting a parallel processing mode to obtain desensitized data corresponding to the data block output by the generative adversarial neural network; and summarizing the desensitized data corresponding to each data block to obtain the desensitized data of the data information. The method is used for avoiding the problems of high calculation cost and limited protection capability of the existing data desensitization.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a data information desensitization method and device, storage medium and processor. BACKGROUND

[0002] Deep learning technology can learn complex patterns and features from large amounts of data, and has shown unprecedented insight in the banking industry. Learning and researching on social security related data has important reference value in credit risk assessment, fraud detection and other aspects. However, the research process of these data also raises important issues of privacy protection, such as identity card numbers, bank account information and other personal sensitive information. Therefore, it is necessary to seek a solution that can meet the needs of scientific research without infringing on personal privacy.

[0003] The current existing data desensitization technical solutions can be roughly divided into the following categories: encryption technology: encrypting data through cryptographic methods to ensure that data cannot be interpreted without authorization; anonymization processing: such as k-anonymity, l-diversity and other technologies, which protect individual identity by generalization or suppression of specific information; data masking: replacing sensitive fields such as phone numbers, addresses and other information before data use.

[0004] However, the current data desensitization technical solutions have the following shortcomings: data processed by encryption technology is difficult to use directly for analysis and needs to be decrypted before use, thereby increasing the computing cost and security risk; data processed by anonymization technology may still have the possibility of privacy leakage when facing advanced attack methods such as link attack and background knowledge attack; data masking achieves privacy protection by replacing sensitive fields, but simple replacement is difficult to resist pattern-based attacks, and has limited protection capability for complex data relationships. SUMMARY

[0005] The purpose of the embodiments of the present application is to provide a data information desensitization method, device, storage medium and processor, which can avoid the problems of high computing cost and limited protection capability of existing data desensitization.

[0006] In order to achieve the above purpose, the first aspect of the present application provides a data information desensitization method, which comprises: acquiring data information and converting the data information into a preset type of data for storage; splitting the stored data based on a preset rule to obtain a plurality of data blocks; using a parallel processing method, inputting each data block into a pre-trained generative adversarial neural network for processing to obtain desensitized data corresponding to the data block output by the generative adversarial neural network; and aggregating the desensitized data corresponding to each data block to obtain desensitized data of the data information.

[0007] In the embodiment of the present application, the data information is obtained from a database or a file, and the preset types include pure text, excel, json and xml.

[0008] In the embodiment of the present application, when the preset type is xml, the data information is obtained, and the data information is converted into data of a preset type for storage, including: obtaining data information of different types; abstracting data structures and data corresponding to each data structure from the data information mapping; storing the data structures to an xml file; storing the data corresponding to each data structure to the xml file; and saving the xml file.

[0009] In the embodiment of the present application, the stored data is split based on a preset rule to obtain a plurality of data blocks, including splitting the stored data into a plurality of data blocks based on a distributed computing framework according to a preset data block size.

[0010] In the embodiment of the present application, the generative adversarial neural network includes: a generator network for generating corresponding preliminary de-sensitization data based on the data information; a differential privacy module for performing differential privacy processing on the generated preliminary de-sensitization data to obtain de-sensitized data; and a discriminator network for comparing data information with the de-sensitized data corresponding to the data information to obtain a comparison result, wherein the comparison result is used to update the parameters of the generator network and the discriminator network during training.

[0011] In the embodiment of the present application, the processing of the generative adversarial neural network on the data block includes performing the following processing on each piece of data in the data block: receiving the data; generating preliminary de-sensitization data corresponding to the data in the generator network based on the data and random noise; and performing differential privacy processing on the preliminary de-sensitization data corresponding to the data based on the differential privacy module to obtain de-sensitized data corresponding to the data.

[0012] The second aspect of the present application provides a data information de-sensitization device, which includes: an acquisition module for acquiring data information and converting the data information into data of a preset type for storage; a splitting module for splitting the stored data based on a preset rule to obtain a plurality of data blocks; a de-sensitization module for inputting each data block to a pre-trained generative adversarial neural network for processing in a parallel processing manner to obtain de-sensitized data corresponding to the data block output by the generative adversarial neural network; and a summary module for summarizing the de-sensitized data corresponding to each data block to obtain de-sensitized data of the data information.

[0013] The third aspect of the present application provides a processor configured to execute the data information desensitization method.

[0014] The fourth aspect of the present application provides a machine readable storage medium having instructions stored thereon, which, when executed by a processor, cause the processor to be configured to execute the data information desensitization method.

[0015] The fifth aspect of the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the data information desensitization method.

[0016] Through the above technical solution, firstly, the acquired data is subjected to heterogeneous data conversion, so that various types of data can be processed; then the stored data is split into multiple data blocks according to the pre-set rules, so that further parallel processing can be performed to realize efficient data processing; for the split data, desensitization is performed based on a generative adversarial neural network, the generated data samples are similar to the original data in statistics, but do not directly correspond to any actual individual data record, thus providing higher level of privacy protection, so that data analysis and scientific research can be directly performed without directly accessing sensitive original data, the calculation cost and security risk of decryption can be reduced, and the possibility of privacy leakage can be reduced.

[0017] Other features and advantages of the embodiments of the present application will be described in detail in the following specific implementation part. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings are included to provide a further understanding of the embodiments of the present application, and constitute a part of the specification, and are used together with the following specific implementation to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the drawings: Figure 1 An application environment schematic diagram of the data information desensitization method according to the embodiments of the present application is schematically shown; Figure 2 A flowchart of the data information desensitization method according to the embodiments of the present application is schematically shown; Figure 3 A structure schematic diagram of the generative adversarial neural network according to the embodiments of the present application is schematically shown; Figure 4 A structure block diagram of the data information desensitization device according to the embodiments of the present application is schematically shown; Figure 5 An internal structure diagram of the computer device according to the embodiments of the present application is schematically shown.

[0019] Explanation of reference signs 400-data information desensitization device; 402 - an acquisition module; 404 - a splitting module; 406 - a desensitization module; 408 - a summarization module. DETAILED DESCRIPTION

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. It should be understood that the specific implementation manners described herein are only used to explain and illustrate the embodiments of the present application and should not be used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort fall within the scope of protection of the present application.

[0021] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back, and the like), the directional indications are only used to explain the relative positional relationship, movement condition, and the like between components in a certain specific posture (as shown in the drawings), and if the specific posture changes, the directional indications also change accordingly.

[0022] In addition, if the embodiments of the present application involve descriptions such as “first”, “second”, and the like, the descriptions of “first”, “second”, and the like are only for description purposes and should not be understood as indicating or implying the relative importance of the technical features indicated or implying the number of the technical features indicated. Therefore, the features limited by “first”, “second” can explicitly or implicitly include at least one of the features. In addition, the technical solutions of the various embodiments can be combined with each other, but it must be based on the fact that a person of ordinary skill in the art can implement it, and when the combination of technical solutions contradicts each other or cannot be implemented, it should be considered that the combination of technical solutions does not exist and is not within the scope of protection claimed by the present application.

[0023] In the technical solutions of the present application, the acquisition, transmission, storage, use, processing, and the like of data comply with the relevant provisions of laws and regulations. In addition, it should be noted that in the embodiments of the present application, some industry existing solutions, components, models, and the like can be mentioned, which should be considered as exemplary, and the purpose is only to illustrate the feasibility of the implementation of the technical solutions of the present application, but it does not mean that the applicant has or will necessarily use the solutions.

[0024] The data information desensitization method provided by the present application can be applied to, for example, Figure 1The application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The server 104 can obtain data information from the terminal 102, and perform desensitization processing on the obtained data information. Among them, the terminal 102 can be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0025] Figure 2 The flowchart of the data information desensitization method according to the embodiment of the application is schematically shown. As Figure 2 shown, in an embodiment of the application, a data information desensitization method is provided, and the embodiment is mainly illustrated by taking the server 104 in the above Figure 1 application environment as an example, including the following steps 202-208.

[0026] Step 202, obtaining data information and converting the data information into a preset type of data for storage.

[0027] Step 204, splitting the stored data based on a preset rule to obtain a plurality of data blocks.

[0028] Step 206, using parallel processing, inputting each of the data blocks into a pre-trained generative adversarial neural network for processing to obtain desensitized data corresponding to the data block output by the generative adversarial neural network.

[0029] Step 208, aggregating the desensitized data corresponding to each of the data blocks to obtain desensitized data of the data information.

[0030] The method provided by the application first converts the obtained data into a preset type of data, so that data of various types can be processed, and the format incompatibility problem that may occur in the data processing process is reduced. Since many data in the bank data are stored in the form of files, the data volume in the big data environment is huge, and the traditional sequential reading and writing cannot meet the requirements, therefore, before desensitizing the data, the stored data is first split into a plurality of data blocks according to the pre-set rule, so that further parallel processing can be performed to realize efficient data processing. After splitting the data information, the desensitization is performed based on the generative adversarial neural network (Generative Adversarial Networks, GAN). Finally, the desensitized data is aggregated to ensure the integrity of the data, and facilitate further analysis or use of the data.

[0031] Employing Generative Adversarial Neural Networks (GANs) for data privacy protection avoids some of the problems associated with existing data anonymization methods. By training a generator to produce new data samples that are statistically similar to the original data but do not directly correspond to any actual individual data records, a higher level of privacy protection is provided, offering better resistance to attacks. Compared to traditional methods, data generated using GANs retains the usability of the data while protecting privacy because it preserves the key characteristics of the original data, rather than simply deleting or modifying sensitive information. Therefore, datasets generated by GANs retain statistical properties similar to real data but do not contain any sensitive information directly pointing to individuals. This allows for data analysis and scientific research without direct access to sensitive original data, reducing the computational cost and security risks of decryption and minimizing the possibility of privacy breaches.

[0032] Figure 2 This is a flowchart illustrating a data anonymization method in one embodiment. It should be understood that, although... Figure 2 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0033] Banking operations involve various data types. Considering the data type of the data masking system, it should support masking in multiple formats, such as from database to database, from database to file, and from file to file. Specifically, databases include traditional Oracle and MySQL, as well as increasingly popular domestic databases like DM and Kingbase. Files include formats such as plain text, Excel, JSON, and XML. Therefore, in step 202, obtaining data information includes retrieving data from a database or a file. The preset types include at least plain text, Excel, JSON, and XML. Data converted to the preset types can then be stored in a database or file for subsequent processing.

[0034] Further, when the preset type is xml, the obtaining data information and converting the data information into data of the preset type for storage comprises: obtaining data information of different types; abstracting data structures and data corresponding to each data structure from the data information mapping; storing the data structures into an xml file; storing the data corresponding to each data structure into the xml file; and saving the xml file.

[0035] Further, the splitting the stored data based on the preset rule to obtain a plurality of data blocks comprises splitting the stored data into a plurality of data blocks based on a distributed computing framework according to a preset data block size.

[0036] The preset data block size can be set according to actual conditions, for example, according to the processing capacity of the system. In specific implementation, a distributed framework, for example, a Spark distributed computing framework, can be used for processing. Such a framework can effectively support the processing requirement of large-scale data.

[0037] Figure 3 An illustrative structure diagram of a generative adversarial neural network according to an embodiment of the present application is shown as follows: Figure 3 As shown, the generative adversarial neural network comprises: a generator network configured to generate corresponding preliminary de-sensitized data based on the data information; a differential privacy module configured to perform differential privacy processing on the generated preliminary de-sensitized data to obtain de-sensitized data; and a discriminator network configured to compare the data information with the de-sensitized data corresponding to the data information to obtain a comparison result, wherein the comparison result is used to update parameters of the generator network and the discriminator network during training.

[0038] The method introduced in the present application introduces differential privacy in the generative adversarial neural network. During the adversarial training of the generative adversarial neural network, the generator network generates preliminary de-sensitized data based on real data and random noise. The preliminary de-sensitized data is not directly input into the discriminator network for comparison with real de-sensitized data, but is first processed by a differential privacy algorithm, and then compared with real de-sensitized data.

[0039] By introducing differential privacy, the dependence of the model on any single training sample during training is significantly reduced. Thus, the trained model is approximately the same regardless of whether a specific sample exists in the training set, avoiding member inference attacks caused by strong dependence on specific samples.

[0040] For the discriminator, it can be trained under differential privacy protection, since only the discriminator can access the real desensitized data, thus through this way, the desensitized data can keep the key characteristics of the original data, and this method can significantly improve the strength of data privacy protection, even in the face of complex deep learning models or membership inference attacks, it can maintain high security. For the generator, it adjusts the parameters according to the feedback information of the discriminator, and then performs independent transformation on the output data through the differential privacy algorithm, ensures that these outputs maintain the characteristics of differential privacy, so that the network meets the differential privacy guarantee.

[0041] Further, the processing of the data block by the generative adversarial neural network includes performing the following processing on each piece of data in the data block: receiving the data; generating preliminary desensitized data corresponding to the data in the generator network based on the data and random noise; and performing differential privacy processing on the preliminary desensitized data corresponding to the data based on the differential privacy module to obtain desensitized data corresponding to the data.

[0042] The data information desensitization method provided by the application constructs an efficient and safe desensitization processing flow. First, the heterogeneous data conversion module realizes the unified formatting processing of multi-source heterogeneous data, improving the scalability of the method; then the distributed computing framework is used to split the data, ensuring the processing efficiency of the system in the big data environment; then the parallel processing is used for the split data, and the data information desensitization algorithm based on the generative adversarial neural network is used for each data block, which fundamentally guarantees the data practicability and security, and significantly improves the strength of privacy protection.

[0043] In one embodiment, as shown in Figure 4 A data information desensitization device is provided, comprising an acquisition module, a splitting module, a desensitization module and a summary module, wherein: The acquisition module 402 is configured to acquire data information and convert the data information into data of a preset type for storage.

[0044] The splitting module 404 is configured to split the stored data based on a preset rule to obtain a plurality of data blocks.

[0045] The desensitization module 406 is configured to input each data block to a pre-trained generative adversarial neural network for processing in a parallel processing manner, to obtain desensitized data corresponding to the data block output by the generative adversarial neural network.

[0046] The summary module 408 is configured to summarize the desensitized data corresponding to each data block to obtain desensitized data of the data information.

[0047] The data information desensitization apparatus includes a processor and a memory, and the acquisition module, the splitting module, the desensitization module, and the summarizing module are all stored in the memory as program units, and the corresponding functions are realized by the processor executing the program modules stored in the memory.

[0048] The processor includes a core, and the core calls the corresponding program units in the memory. The core can be one or more, and the data information desensitization method is realized by adjusting the core parameters.

[0049] The memory can include a non-permanent memory in a computer readable medium, a random access memory (RAM), and / or a non-volatile memory such as a read-only memory (ROM) or a flash memory (flash RAM), and the memory includes at least one memory chip.

[0050] Embodiments of the present application provide a processor, which is used to run a program, wherein the program performs the data information desensitization method when running.

[0051] Embodiments of the present application provide a machine readable storage medium, which stores instructions, and the instructions make the processor be configured to perform the data information desensitization method when executed by the processor.

[0052] In one embodiment, a computer device can be provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 5 The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure), and a database (not shown in the figure) connected through a system bus. The processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown in the figure). The internal memory A03 provides an environment for the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store data information and desensitized data. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. The computer program B02 is executed by the processor A01 to realize a data information desensitization method.

[0053] Those skilled in the art can understand that, Figure 5The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0054] In one embodiment, the data information desensitization apparatus provided by the present application can be implemented in the form of a computer program, which can run on a computer device as shown in the figure. The memory of the computer device can store various program modules constituting the data information desensitization apparatus, such as the acquisition module, the splitting module, the desensitization module, and the summarizing module shown in the figure. The computer program constituted by the various program modules causes the processor to execute the steps in the data information desensitization method of each embodiment of the present application described in the specification. Figure 5 Figure 4 The computer device shown in the figure can execute step 202 by the acquisition module 402 in the data information desensitization apparatus, execute step 204 by the splitting module 404, execute step 206 by the desensitization module 406, and execute step 208 by the summarizing module 408.

[0055] Figure 5 The computer device shown in the figure can execute step 202 by the acquisition module 402 in the data information desensitization apparatus, execute step 204 by the splitting module 404, execute step 206 by the desensitization module 406, and execute step 208 by the summarizing module 408. Figure 4

[0056] The present application provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. The processor executes the program to implement the steps of the data information desensitization method.

[0057] The present application also provides a computer program product adapted to execute the steps of the data information desensitization method when executed on a data processing device.

[0058] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0059] ​​The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0060] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0061] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0062] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0063] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory, for storing instructions and data used and / or generated by the computing device. The memory can also include non-volatile memory, such as read-only memory (ROM), electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other non-volatile memory.

[0064] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can implement information storage by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0065] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not only include those elements, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0066] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A method for desensitizing data information, characterized in that, The method includes: Acquire data information and convert the data information into data of a preset type for storage; The stored data is split into multiple data blocks based on preset rules; Using parallel processing, each data block is input into a pre-trained generative adversarial neural network (GAN) for processing, resulting in de-identified data corresponding to that data block output by the GAN; and The anonymized data corresponding to each data block is summarized to obtain the anonymized data of the data information.

2. The method according to claim 1, characterized in that, The data information comes from a database or file, and the preset types include plain text, Excel, JSON, and XML.

3. The method according to claim 1, characterized in that, When the preset type is XML, acquiring data information and converting the data information into data of the preset type for storage includes: Acquire different types of data information; The data information is mapped and abstracted to form data structures and corresponding data for each data structure. The data structures include field names, types, keys, and comments. Store the data structure in an XML file; Store the corresponding data for each data structure into an XML file; and Save the XML file.

4. The method according to claim 1, characterized in that, The stored data is split into multiple data blocks based on preset rules, including splitting the stored data into multiple data blocks according to preset data block sizes based on a distributed computing framework.

5. The method according to claim 1, characterized in that, The generative adversarial neural network includes: A generator network is used to generate corresponding preliminary de-identified data based on the data information; A differential privacy module is used to perform differential privacy processing on the generated preliminary de-identified data to obtain de-identified data; and The discriminator network is used to compare the data information with the corresponding de-identified data to obtain a comparison result. The comparison result is used to update the parameters of the generator network and the discriminator network during training.

6. The method according to claim 5, characterized in that, The generative adversarial neural network processes the data block by performing the following processing on each piece of data in the data block: Receive the data; Based on the data and random noise, preliminary de-identified data corresponding to the data is generated in the generator network; as well as Based on the differential privacy module, differential privacy processing is performed on the preliminary de-identified data corresponding to the data to obtain the de-identified data corresponding to the data.

7. A data information desensitization device, characterized in that, The device includes: The acquisition module is used to acquire data information and convert the data information into data of a preset type for storage. The splitting module is used to split the stored data into multiple data blocks based on preset rules; The desensitization module is used to process each data block in parallel by inputting it into a pre-trained generative adversarial neural network (GAN) to obtain the desensitized data corresponding to that data block output by the GAN; and The aggregation module is used to aggregate the de-identified data corresponding to each data block to obtain the de-identified data of the data information.

8. A processor, characterized in that, It is configured to perform the data information desensitization method according to any one of claims 1 to 6.

9. A machine-readable storage medium storing instructions thereon, characterized in that, When executed by a processor, this instruction causes the processor to be configured to perform the data information desensitization method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the data information desensitization method according to any one of claims 1 to 6.

Images